Multilayer residual sparsifying transform (MARS) model for low-dose CT image reconstruction.
low-dose CT
sparse representation
statistical image reconstruction
transform learning
unsupervised learning
Journal
Medical physics
ISSN: 2473-4209
Titre abrégé: Med Phys
Pays: United States
ID NLM: 0425746
Informations de publication
Date de publication:
Oct 2021
Oct 2021
Historique:
revised:
14
05
2021
received:
10
10
2020
accepted:
19
05
2021
pubmed:
14
9
2021
medline:
6
11
2021
entrez:
13
9
2021
Statut:
ppublish
Résumé
Signal models based on sparse representations have received considerable attention in recent years. On the other hand, deep models consisting of a cascade of functional layers, commonly known as deep neural networks, have been highly successful for the task of object classification and have been recently introduced to image reconstruction. In this work, we develop a new image reconstruction approach based on a novel multilayer model learned in an unsupervised manner by combining both sparse representations and deep models. The proposed framework extends the classical sparsifying transform model for images to a Multilayer residual sparsifying transform (MARS) model, wherein the transform domain data are jointly sparsified over layers. We investigate the application of MARS models learned from limited regular-dose images for low-dose CT reconstruction using penalized weighted least squares (PWLS) optimization. We propose new formulations for multilayer transform learning and image reconstruction. We derive an efficient block coordinate descent algorithm to learn the transforms across layers, in an unsupervised manner from limited regular-dose images. The learned model is then incorporated into the low-dose image reconstruction phase. Low-dose CT experimental results with both the XCAT phantom and Mayo Clinic data show that the MARS model outperforms conventional methods such as filtered back-projection and PWLS methods based on the edge-preserving (EP) regularizer in terms of two numerical metrics (RMSE and SSIM) and noise suppression. Compared with the single-layer learned transform (ST) model, the MARS model performs better in maintaining some subtle details. This work presents a novel data-driven regularization framework for CT image reconstruction that exploits learned multilayer or cascaded residual sparsifying transforms. The image model is learned in an unsupervised manner from limited images. Our experimental results demonstrate the promising performance of the proposed multilayer scheme over single-layer learned sparsifying transforms. Learned MARS models also offer better image quality than typical nonadaptive PWLS methods.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
6388-6400Subventions
Organisme : NSFC
ID : 61501292
Informations de copyright
© 2021 American Association of Physicists in Medicine.
Références
Chen G-H, Tang J, Leng S. Prior image constrained compressed sensing (PICCS): a method to accurately reconstruct dynamic CT images from highly undersampled projection data sets. Med Phys. 2008;35:660-663.
Mairal J, Elad M, Sapiro G. Sparse representation for color image restoration. IEEE Trans Im Proc. 2008;17:53-69.
Elad M, Aharon M. Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans Im Proc. 2006;15:3736-3745.
Zhang Y, Mou X, Wang G, Yu H. Tensor-based dictionary learning for spectral CT reconstruction. IEEE Trans Med Imaging. 2017;36:142-154.
Pati Y, Rezaiifar R, Krishnaprasad P. Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition. In: Asilomar Conf. on Signals, Systems and Computers, vol. 1. 1993:40-44.
Aharon M, Elad M, Bruckstein A. K-SVD: an algorithm for designing over-complete dictionaries for sparse representation. IEEE Trans Sig Proc. 2006;54:4311-4322.
Rubinstein R, Peleg T, Elad M. Analysis K-SVD: a dictionary-learning algorithm for the analysis sparse model. IEEE Trans Sig Proc. 2013;61:661-677.
Le Magoarou L, Gribonval R. Chasing butterflies: In search of efficient dictionaries. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015:3287-3291.
Ravishankar S, Bresler Y. Learning sparsifying transforms. IEEE Trans Sig Proc. 2013;61:1072-1086.
Ravishankar S, Bresler Y. Data-driven learning of a union of sparsifying transforms model for blind compressed sensing. IEEE Trans Comput Imaging. 2016;2:294-309.
Wen B, Li Y, Bresler Y. When sparsity meets low-rankness: Transform learning with non-local low-rank constraint for image restoration. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017:2297-2301.
Wen B, Ravishankar S, Bresler Y. VIDOSAT: high-dimensional sparsifying transform learning for online video denoising. IEEE Trans Image Process. 2019;28:1691-1704.
LeCun Y, Bengio Y, Hionton G. Deep learning. Nature. 2015;521:436-444.
Patel A, Nguyen T, Baraniuk R. A probabilistic framework for deep learning. In: Conference and Workshop on Neural Information Processing Systems (NIPS), 2016.
Papyan V, Romano Y, Elad M. Convolutional neural networks analyzed via convolutional sparse coding. J Mach Learn Res. 2016;18:2887-2938.
Sulam J, Papyan V, Romano Y, Elad M. Multilayer convolutional sparse modeling: pursuit and dictionary learning. IEEE Trans. Signal Process. 2018;66:4090-4104.
Ravishankar S, Wohlberg B. Learning multi-layer transform models. In: Allerton Conf. on Comm., Control, and Computing, 2018:160-165.
Feldkamp LA, Davis LC, Kress JW. Practical cone beam algorithm. J Opt Soc Am A. 1984;1:612-619.
Elbakri IA, Fessler JA. Statistical image reconstruction for polyenergetic X-ray computed tomography. IEEE Trans. Med. Image. 2002;21:89-99.
Sauer K, Bouman C. A local update strategy for iterative reconstruction from projections. IEEE Trans Sig Proc. 1993;41:534-548.
Thibault J-B, Bouman CA, Sauer KD, Hsieh J. A recursive filter for noise reduction in statistical iterative tomographic imaging. In: Proc. SPIE, vol. 6065, 2006:60650X-1-60650X-10.
Thibault J-B, Sauer K, Bouman C, Hsieh J. A three-dimensional statistical approach to improved image quality for multi-slice helical CT. Med Phys. 2007;34:4526-4544.
Pfister L, Bresler Y. Model-based iterative tomographic reconstruction with adaptive sparsifying transforms. In: Proc. SPIE, vol. 9020, 2014:90200H-1-90200H-11.
Pfister L, Bresler Y. Tomographic reconstruction with adaptive sparsifying transforms. In: Proc. IEEE Conf. Acoust. Speech Sig. Proc., 2014:6914-6918.
Pfister L, Bresler Y. Adaptive sparsifying transforms for iterative tomographic reconstruction. In: Proc. 3rd Intl. Mtg. on image formation in X-ray CT, 2014:107-110.
Zheng X, Ravishankar S, Long Y, Fessler JA. PWLS-ULTRA: an efficient clustering and learning-based approach for low-dose 3D CT image reconstruction. IEEE Trans Med Imag. 2018;37:1498-1510.
Chun IY, Zheng X, Long Y, Fessler JA. Efficient sparse-view X-ray CT reconstruction using ℓ1 regularization with learned sparsifying transform. In: Proc. Intl. Mtg. on Fully 3D Image Recon. in Rad. and Nuc. Med, 2017:115-119.
Ye S, Ravishankar S, Long Y, Fessler JA. SPULTRA: low-dose CT image reconstruction with joint statistical and learned image models. IEEE Trans Med Imaging. 2020;39:729-741.
Zhou W, Cai J-F, Gao H. Adaptive tight frame based medical image reconstruction: a proof-of-concept study for computed tomography Inverse Prob. 2013;29:125006.
Ravishankar S, Bresler Y. ℓ0 Sparsifying transform learning with efficient optimal updates and convergence guarantees. IEEE Trans Sig Proc. 2015;63:2389-2404.
Nien H, Fessler JA. Relaxed linearized algorithms for faster X-ray CT image reconstruction. IEEE Trans Med Imag. 2016;35:1090-1098.
Cho JH, Fessler JA. Regularization designs for uniform spatial resolution and noise properties in statistical image reconstruction for 3D X-ray CT. IEEE Trans Med Imag. 2015;34:678-689.
Xu Q, Yu H, Mou X, Zhang L, Hsieh J, Wang G. Low-dose X-ray CT reconstruction via dictionary learning. IEEE Trans Med Imaging. 2012;31:1682-1697.
Ding Q, Long Y, Zhang X, Fessler JA. Modeling mixed Poisson-Gaussian noise in statistical image reconstruction for X-ray CT. In: Proc. 4th Intl. Mtg. on image formation in X-ray CT. 2016:399-402.
Segars WP, Mahesh M, Beck TJ, Frey EC, Tsui BMW. Realistic CT simulation using the 4D XCAT phantom. Med Phys. 2008;35:3800-3808.
McCollough C. TU-FG-207A-04: overview of the low dose CT grand challenge. Med Phys. 2016;43:3759-60.
Singhal V, Maggu J, Majumdar A. Simultaneous detection of multiple appliances from Smart-Meter measurements via multi-label consistent deep dictionary learning and deep transform learning. IEEE Trans Smart Grid. 2019;10:2969-2978.